PMLEP 2016 - Special session on Physics and Machine Learning: Emerging Paradigms

The current research of Machine Learning (ML) combines the study of variations to well-?‐established methods with cutting-?‐edge breakthroughs based on completely new approaches. Among the latter, emerging paradigms from Physics have taken special relevance in recent years. Although still in its initial stages, Quantum Machine Learning shows promising ways to speed up some of the costly ML calculations with a similar or even better performance. Two additional advantages are related to the intrinsic probabilistic approach of QML, since quantum states are genuinely probabilistic, and to the fact of finding the global minimum of a given function by means of adiabatic quantum optimization, thus circumventing the usual problem of local minima. Another Physics approach for ML comes from Statistical Physics that is linked to Information theory in supervised and semi-?‐supervised learning frameworks.
The community working on new ML approaches from Physics is not large, and it is very important to meet up with other colleagues to show your advances and being up to date with those of others. This special session is aimed at providing a discussion forum for researchers working on emerging paradigms for ML, especially those related (but not restricted) to Physics; new paradigm proposals from other fields are also welcome.
The main topics of the session include, but are not limited to, theoretical developments in, and applications of:
Quantum clustering.
Quantum Principal Component Analysis.
Quantum Support Vector Machines.
Quantum neural networks.
Quantum regression.
Grover’s search algorithms.
Adiabatic quantum optimization.
Information theoretic methods for supervised and semi-supervised learning.
Other cutting-edge ML and data analysis approaches: natural language processing; analysis of heterogeneous data and meta-data; mining incomplete and/or streaming data, etc.